More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Context Window Tracker

    2

    Monitor and analyze real-time context window usage with visual bars and detailed token breakdowns.

    Free

    18 usesSecurity scanned

    context-window-tracker

    Example session with this skill installed

    Give me a detailed breakdown of my current context window usage and let me know if I have enough room to finish this refactor.

    • Read your context and instructions
    • Compiled the context-window-tracker

    🟒 [β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘] Context Usage: 113.7K / 202.8K (56%) **Detailed Breakdown** β€’ System Prompt: ~10.2K β€’ Conversation: ~103.5K β€’ Avg per turn: ~316 tokens β€’ Estimated turns remaining: ~281 **Guidance:** Plenty of room to finish the current refactor.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Optimize Your AI Workflows

    Context Window Tracker is a specialized utility for developers using OpenClaw who need to monitor token consumption in real-time. It prevents the sudden "context full" errors that derail complex coding sessions by providing transparency into exactly how your context budget is being spent.

    What it does

    The skill analyzes your active session transcript and system files to generate readable usage reports. It supports two modes:

    • Compact: A one-line visual progress bar with vital stats (Total usage, % full, estimated turns remaining).
    • Detailed: A deep-dive breakdown showing which specific files (like SOUL.md or TOOLS.md) are consuming the most tokens, alongside conversation history and framework overhead.

    Why use this skill?

    Unlike basic AI prompting which can only guess its usage, this tool reads the underlying session .jsonl files to provide accurate data. It includes a smart health indicator (Green/Yellow/Red) and provides contextual guidance on whether you have enough room to finish your current task or should start a fresh session.

    Supported Features

    • Per-file token breakdown for system prompts.
    • Trend analysis to estimate remaining turns based on session velocity.
    • Cache hit rate tracking for cost efficiency.
    • Optional auto-check mode that triggers every 10 messages.

    Cant be used on agents with web UI's such as Chatgpt.com or Claude.ai. Best used in frameworks like Clawhub, Claude code etc

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    18 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 6 months ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Read Files
    Listed6 months ago

    What's inside

    Frequently Asked Questions

    This skill prevents 'out of context' errors by providing real-time visibility into token usage, helping you decide when to prune files or refresh a session before a task fails.

    The skill works by analyzing OpenClaw's session logs and .jsonl files, making it compatible with any AI agent or architecture running on the OpenClaw framework.

    Yes, you can toggle between 'Compact' mode for a quick visual status bar and 'Detailed' mode for a granular file-by-file breakdown of what is consuming your tokens.

    The tracker uses a specialized algorithm to read active session files, providing a more precise measurement of 'system overhead' and file consumption than standard message counters.

    Your purchase includes the full skill package, a quick-start integration guide, and lifetime access to any performance updates or new analytical features released for the tool.

    New in Agents & Orchestration